Generating a video presentation to accompany audio

Abstract

Example methods and systems for generating a video presentation to accompany audio are described. The video presentation to accompany the audio track is generated from one or more video sequences. In some example embodiments, the video sequences are divided into video segments that correspond to discontinuities between frames. Video segments are concatenated to form a video presentation to which the audio track is added. In some example embodiments, only video segments having a duration equal to an integral number of beats of music in the audio track are used to form the video presentation. In these example embodiments, transitions between video segments in the video presentation that accompanies the audio track are aligned with the beats of the music.

What is claimed is: 
     
       1. A system comprising:
 a memory that stores instructions; 
 one or more databases that store a plurality of music tracks and a plurality of video sequences; and 
 one or more processors configured by the instructions to perform operations comprising: 
 accessing a music track from the one or more databases, the music track having a tempo corresponding to a frequency of beats in the music track and one or more portions; 
 accessing an individual video sequence from the one or more databases; 
 measuring respective distances between successive frames in the individual video sequence; 
 based on a plurality of the respective distances between successive frames in the individual video sequence, identifying transitions within the individual video sequence, wherein the identified transitions include a first transition after a beginning of the individual video sequence and a second transition before an end of the individual video sequence, and wherein the identified transitions indicate one or more events of the individual video sequence; and 
 generating an audio/video sequence that comprises the individual video sequence and at least one of the one or more portions of the music track, wherein the at least one of the one or more portions of the music track is a subset portion of at least one of: (i) a chorus of the music track; and (ii) a verse of the music track, and wherein generating the audio/video sequence comprises modifying a duration of the individual video sequence between the first and second transitions so that the first and second transitions align with respective beats of the at least one of the one or more portions of the music track and identifying the at least one of the one or more portions of the music track based on a duration of the audio/video sequence. 
 
     
     
       2. The system of  claim 1 , wherein:
 the operations further comprise receiving a selection of a tempo; and 
 the accessing of the music tracks from the one or more databases is based on the selected tempo and the tempos of the music tracks. 
 
     
     
       3. The system of  claim 1 , wherein:
 the operations further comprise accessing a search query; and 
 the accessing of the individual video sequence from the one or more databases is based on the search query. 
 
     
     
       4. The system of  claim 1 , wherein:
 modifying the duration of the individual video sequence between the first and second transitions comprises modifying the duration of the individual video sequence between the first and second transitions to be an integral multiple of a beat period of the music track. 
 
     
     
       5. The system of  claim 1 , wherein:
 the generating of the audio/video sequence comprises generating the audio/video sequence with a predetermined duration. 
 
     
     
       6. The system of  claim 1 , wherein:
 the generating of the audio/video sequence comprises generating the audio/video sequence with a duration equal to the duration of the music track. 
 
     
     
       7. The system of  claim 1 , wherein:
 the generating of the audio/video sequence comprises generating the audio/video sequence with a user-selected duration. 
 
     
     
       8. The system of  claim 1 , wherein:
 the accessing of the individual video sequence comprises selecting the individual video sequence from among a plurality of video sequences based on the tempo of the music track. 
 
     
     
       9. The system of  claim 1 , wherein:
 the accessing of the individual video sequence comprises selecting the individual video sequence from among a plurality of video sequences based on the tempo of the music track. 
 
     
     
       10. The system of  claim 1 , wherein the one or more events comprise events other than scene transitions. 
     
     
       11. The system of  claim 1 , wherein the operations further comprise determining that a distance between at least two successive frames exceeds a predetermined threshold, wherein determining that a distance between at least two successive frames exceeds a predetermined threshold comprises generating a sum of the absolute values of differences in color values of corresponding pixels in each of at least two successive frames and determining that the differences exceed a predetermined threshold. 
     
     
       12. The system of  claim 1 , wherein modifying a duration of the individual video sequence between the first and second transitions comprises duplicating at least one frame of the individual video sequence between the first and second transitions. 
     
     
       13. The system of  claim 1 , wherein modifying a duration of the individual video sequence between the first and second transitions comprises deleting at least one frame of the individual video sequence between the first and second transitions. 
     
     
       14. A method comprising:
 accessing, by one or more processors, a music track from an audio database, the music track having a tempo corresponding to a frequency of beats in the music track and one or more portions; 
 accessing, by the one or more processors, an individual video sequence from a video database; 
 measuring respective distances between successive frames in the individual video sequence; 
 based on a plurality of the respective distances between successive frames in the individual video sequence, identifying, by the one or more processors, transitions within the individual video sequence, wherein the identified transitions include a first transition after a beginning of the individual video sequence and a second transition before an end of the individual video sequence, and wherein the identified transitions indicate one or more events of the individual video sequence; and 
 generating, by the one or more processors, an audio/video sequence that comprises the individual video sequences and at least one of the one or more portions of the music tracks, wherein the at least one of the one or more portions of the music track is a subset portion of at least one of: (i) a chorus of the music track; and (ii) a verse of the music track, and wherein generating the audio/video sequence comprises modifying a duration of the individual video sequence between the first and second transitions so that the first and second transitions align with respective beats of the at least one of the one or more portions of the music track and identifying the at least one of the one or more portions of the music track based on a duration of the audio/video sequence. 
 
     
     
       15. The method of  claim 14 , further comprising:
 receiving a selection of a tempo; and 
 wherein the accessing of the music tracks from the audio database is based on the selected tempo and the tempos of the music tracks. 
 
     
     
       16. The method of  claim 14 , further comprising:
 accessing a search query; and 
 wherein the accessing of the individual video sequence from the video database is based on the search query. 
 
     
     
       17. The method of  claim 14 , wherein:
 modifying the duration of the individual video sequence between the first and second transitions comprises modifying the duration of the individual video sequence between the first and second transitions to be an integral multiple of a beat period of the music track. 
 
     
     
       18. The method of  claim 14 , wherein:
 the generating of the audio/video sequence comprises generating the audio/video sequence with a predetermined duration. 
 
     
     
       19. The method of  claim 14 , wherein:
 the generating of the audio/video sequence comprises generating the audio/video sequence with a duration equal to the duration of the music track. 
 
     
     
       20. The method of  claim 14 , wherein:
 the generating of the audio/video sequence comprises generating the audio/video sequence with a user-selected duration. 
 
     
     
       21. A non-transitory machine-readable medium comprising instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:
 accessing a music track from an audio database, the music track having a tempo corresponding to a frequency of beats in the music track and one or more portions, wherein each of the one or more portions of the music track correspond to a part of the music track; 
 accessing an individual video sequence from a video database; 
 measuring respective distances between successive frames m the individual video sequence; 
 based on a plurality of the respective distances between successive frames in the individual video sequence, identifying transitions within the individual video sequence, wherein the identified transitions include a first transition after a beginning of the individual video sequence and a second transition before an end of the individual video sequence, and wherein the identified transitions indicate one or more events of the individual video sequence; and 
 generating an audio/video sequence that comprises the individual video sequence and at least one of the one or more portions of the music tracks, wherein the at least one of the one or more portions of the music track is a subset portion of at least one of: (i) a chorus of the music track; and (ii) a verse of the music track, and wherein generating the audio/video sequence comprises modifying a duration of the individual video sequence between the first and second transitions so that the first and second transitions so that the first and second transitions align with respective beats of the at least one of the one or more portions of the music track and identifying the at least one of the one or more portions of the music track based on a duration of the audio/video sequence. 
 
     
     
       22. The non-transitory machine-readable medium of  claim 21 , wherein:
 the operations further comprise receiving a selection of a tempo; and 
 the accessing of the music tracks from the audio database is based on the selected tempo and the tempos of the music tracks. 
 
     
     
       23. The non-transitory machine-readable medium of  claim 21 , wherein:
 the operations further comprise accessing a search query; and 
 the accessing of the individual video sequence from the video database is based on the search query. 
 
     
     
       24. The non-transitory machine-readable medium of  claim 21 , wherein:
 the accessing of the individual video sequence comprises selecting the individual video sequence from among a plurality of video sequences based on the tempo of the music track.